Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

• URL: http://arxiv.org/abs/2106.00445v1
• Date: Tue, 1 Jun 2021 12:53:53 GMT
• Title: Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
• Authors: Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama
• Abstract summary: In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels, and thus large-loss data are likely but not certainly to be incorrect. In this paper, we incorporate the uncertainty of losses by adopting interval estimation instead of point estimation of losses.
• Score: 145.06552420999986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels, and thus large-loss data are likely but not certainly to be incorrect. There are actually two possibilities of a large-loss data point: (a) it is mislabeled, and then its loss decreases slower than other data, since deep neural networks "learn patterns first"; (b) it belongs to an underrepresented group of data and has not been selected yet. In this paper, we incorporate the uncertainty of losses by adopting interval estimation instead of point estimation of losses, where lower bounds of the confidence intervals of losses derived from distribution-free concentration inequalities, but not losses themselves, are used for sample selection. In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try. As a result, we can better explore underrepresented data that are correctly labeled but seem to be mislabeled at first glance. Experiments demonstrate that the proposed method is superior to baselines and robust to a broad range of label noise types.

Related papers

• Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification [6.920336485308536]
  Pseudo-labeling-based semi-supervised approaches suffer from two problems in image classification. We develop a self adaptive threshold pseudo-labeling strategy, which thresholds for each class can be dynamically adjusted to increase the number of reliable samples. In order to effectively utilise unlabeled data with confidence below the thresholds, we propose an unreliable sample contrastive loss.
  arXiv  Detail & Related papers  (2024-07-04T03:04:56Z)
• Late Stopping: Avoiding Confidently Learning from Mislabeled Examples [61.00103151680946]
  We propose a new framework, Late Stopping, which leverages the intrinsic robust learning ability of DNNs through a prolonged training process. We empirically observe that mislabeled and clean examples exhibit differences in the number of epochs required for them to be consistently and correctly classified. Experimental results on benchmark-simulated and real-world noisy datasets demonstrate that the proposed method outperforms state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2023-08-26T12:43:25Z)
• Partial-Label Regression [54.74984751371617]
  Partial-label learning is a weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels. Previous studies on partial-label learning only focused on the classification setting where candidate labels are all discrete. In this paper, we provide the first attempt to investigate partial-label regression, where each training example is annotated with a set of real-valued candidate labels.
  arXiv  Detail & Related papers  (2023-06-15T09:02:24Z)
• Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation [21.163070161951868]
  Semi-consuming learning (SSL) can reduce the need for large labelled datasets by incorporating unsupervised data into the training. Current SSL approaches use an initially supervised trained model to generate predictions for unlabelled images, called pseudo-labels. We use three mechanisms to control pseudo-label noise and errors.
  arXiv  Detail & Related papers  (2022-10-19T09:46:27Z)
• Adaptive Sample Selection for Robust Learning under Label Noise [1.71982924656402]
  Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily labelled data. A prominent class of algorithms rely on sample selection strategies, motivated by curriculum learning. We propose a data-dependent, adaptive sample selection strategy that relies only on batch statistics.
  arXiv  Detail & Related papers  (2021-06-29T12:10:58Z)
• Learning from Noisy Labels via Dynamic Loss Thresholding [69.61904305229446]
  We propose a novel method named Dynamic Loss Thresholding (DLT) During the training process, DLT records the loss value of each sample and calculates dynamic loss thresholds. Experiments on CIFAR-10/100 and Clothing1M demonstrate substantial improvements over recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-01T07:59:03Z)
• Minimax Active Learning [61.729667575374606]
  Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. We develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner.
  arXiv  Detail & Related papers  (2020-12-18T19:03:40Z)
• Improving Generalization of Deep Fault Detection Models in the Presence of Mislabeled Data [1.3535770763481902]
  We propose a novel two-step framework for robust training with label noise. In the first step, we identify outliers (including the mislabeled samples) based on the update in the hypothesis space. In the second step, we propose different approaches to modifying the training data based on the identified outliers and a data augmentation technique.
  arXiv  Detail & Related papers  (2020-09-30T12:33:25Z)
• Learning with Out-of-Distribution Data for Audio Classification [60.48251022280506]
  We show that detecting and relabelling certain OOD instances, rather than discarding them, can have a positive effect on learning. The proposed method is shown to improve the performance of convolutional neural networks by a significant margin.
  arXiv  Detail & Related papers  (2020-02-11T21:08:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.